academic-plotting

Generates publication-quality figures for ML papers from research context. Given a paper section or description, extracts system components and relationships to generate architecture diagrams via Gemini. Given experiment results or data, auto-selects chart type and generates data-driven figures via matplotlib/seaborn. Use when creating any figure for a conference paper.

Quality

75%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Passed

No findings from the security scan

Fix and improve this skill with Tessl

tessl review fix ./skills/vendor-ai-research/academic-plotting/SKILL.md

Quality

Content

67%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, highly actionable skill body with executable chart code, decision tables, and checklists for both workflows, supported by real one-level reference files. The main drag is conciseness: the four inlined visual-style blocks add length that overlaps with the referenced detail file.

Suggestions

Move the four full visual-style blocks (Sketch / Modern Minimal / Illustrated / Accent Bar) and the curated color-palette list into references/diagram-generation.md, keeping only a one-line summary and style-selection guidance in SKILL.md.

Add an explicit validation checkpoint to the Workflow 2 checklist (e.g. 'Render and confirm the figure fits the venue column width; regenerate if labels overlap or fonts fail in LaTeX').

Provide a concrete filled-in example of the 6-section Gemini prompt (not just the placeholder) so the generation script is runnable end-to-end without hand-authoring.

Dimension	Reasoning	Score
Conciseness	The ~470-line body is mostly actionable rather than padded with concepts Claude already knows, but it inlines four full visual-style blocks (~80 lines) plus several color palettes that overlap with the referenced diagram-generation.md and could be tightened or moved out of the main file.	3 / 5
Actionability	Provides copy-paste-ready matplotlib/seaborn code for line, grouped-bar, heatmap, and horizontal-bar patterns plus a publication-styling template, but the Gemini generation script carries a '[PASTE YOUR 6-SECTION PROMPT HERE]' placeholder and requires hand-authoring a 50–150 line LAYOUT section, a minor gap in full executability.	4 / 5
Workflow Clarity	Both workflows have explicit checklists and a numbered extraction sequence, with a Gemini 3-attempt retry loop and a Common Issues troubleshooting table for error recovery, but the data-chart workflow lacks an explicit validate-output-then-fix checkpoint.	4 / 5
Progressive Disclosure	Clear section structure with three well-signaled, one-level-deep references (diagram-generation.md, data-visualization.md, style-guide.md) that all exist, but the inlined style blocks and palettes are content that arguably belongs in the reference file, a minor organization gap.	4 / 5
	Total	15 / 20 Passed

Description

83%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, specific, third-person description that concretely covers both the diagram and data-figure workflows and names the relevant tools. The main weakness is the single, somewhat broad 'Use when' trigger, which keeps completeness and trigger-term quality just below the top anchor.

Suggestions

Expand the 'Use when' clause with concrete trigger phrases, e.g. 'Use when creating architecture diagrams, training curves, ablation charts, or any figure for an ML conference paper'.

Add common natural synonyms users say ('plot', 'ablation', 'training curve', 'scaling-law plot') to broaden trigger coverage.

Dimension	Reasoning	Score
Specificity	Lists multiple concrete actions across both workflows — 'extracts system components and relationships to generate architecture diagrams via Gemini' and 'auto-selects chart type and generates data-driven figures via matplotlib/seaborn' — giving comprehensive coverage.	5 / 5
Completeness	Clearly answers 'what' (two figure-generation workflows) and gives an explicit 'when' clause ('Use when creating any figure for a conference paper'), but the trigger is a single general condition rather than the rich set of concrete trigger phrases that define the top anchor.	4 / 5
Trigger Term Quality	Good natural keyword coverage ('figures', 'ML papers', 'conference paper', 'architecture diagrams', 'data-driven figures', 'matplotlib/seaborn'), but a few natural variations (e.g. 'plot', 'ablation', 'training curves') and any file-extension triggers are missing, so it stops short of the comprehensive-synonym anchor.	4 / 5
Distinctiveness Conflict Risk	Scoped to a clear niche — publication figures for ML conference papers via two distinct tool paths (Gemini diagrams, matplotlib/seaborn data charts) — with distinct triggers and minimal overlap with general-purpose plotting or diagramming skills.	5 / 5
	Total	18 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
frontmatter_unknown_keys	Unknown frontmatter key(s) found; consider removing or moving to metadata	Warning

	Total	15 / 16 Passed

Repository: OpenRaiser/NanoResearch
Path: skills/vendor-ai-research/academic-plotting/SKILL.md
Commit: 9d3b440

Reviewed: 11 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.